Two years ago, Gal Salomon’s mother developed sepsis during a stay in the hospital. “It was a big hospital with a lot of patients and no one saw or understood it was happening,” Salomon recalls bitterly. “We lost her after two days.”
So when Salomon, then a partner at Israeli venture capital firm Pitango, was introduced to Clew Medical, he knew immediately that he had to get involved. Clew develops software that uses artificial intelligence (AI) to predict which patients in a hospital’s intensive care unit (ICU) are at the highest risk of imminent deterioration, and it alerts staff so they can intervene early.
Hospitals today run according to evidence-based medicine, explains Salomon, who is now Clew’s CEO. That makes for smart science. But for critical care, it can be a problem.
“You need to make sure something is happening 100 percent before you take action,” Salomon tells ISRAEL21c. A patient may appear normal, “but if you had a sign that, in two to three hours, that patient will need a major intervention, if you don’t do it now, you are already too late. The biggest problem in the ICU is that we don’t respond in time.”
Clew’s software connects to the ICU’s systems – for example, those that track blood pressure and heart rate – and pairs it with data from a patient’s electronic medical record.
Clew then adds a third element – the cloud. Using AI, Clew can match a patient’s history and current vital signs with knowledge from thousands of other patients in similar situations to predict the patient’s trajectory more accurately than an overworked doctor or nurse can.
For example, Clew can identify the patients who are most likely to become unstable, along with the source and kind of deterioration they may encounter. It can predict how long a patient will need to be connected to a ventilator or a dialysis machine, and when a patient will be ready to be discharged.
Clew has built the capacity to process real-time updates coming from the many devices in the ICU, where blood pressure is measured every few seconds. “We track hundreds of parameters coming in high frequency,” Salomon explains.
That can also help the ICU staff with resource management. “We can tell them that if they have 20 beds, here’s where they should put those resources,” Salomon says. “Here are the patients who need a dedicated nurse, here are the patients who are stable. Here’s how to manage your team in a more efficient way.”
Clew’s own team is composed of both doctors and mathematicians. Salomon is from neither discipline. An engineer by training, he worked for Intel and DSP Communications before joining Pitango. He also founded Sansa Security, which he sold to ARM. So Salomon is no stranger to technology.
But using technology to “save lives is something important,” he tells ISRAEL21c. “We see around us many companies with very talented guys using AI to get you to read more articles or do more shopping. This is completely different.”
Clew has been in proof-of-concept testing at Sheba and Ichilov hospitals in Israel, and the Mayo and Cleveland clinics in the United States. The next step is FDA clearance.
“Our customers don’t actually require us to be FDA approved, but we decided this was the right thing to do,” Salomon says. The company will be on display at the HIMSS (Health Information and Management Systems Society) conference in Las Vegas in March, where Salomon says Clew will announce the results of the testing at the Mayo Clinic “and probably one to two other commercial products as well.”
The 26-person Netanya-based company, founded in 2014, has raised just over $10 million and is now looking for another $20 million in 2018. In addition to reaching out to more hospitals, the money will help Clew more effectively harness the power of the cloud.
Currently, Clew engineers have to install a dedicated PC at each hospital ICU. That makes it hard to scale: Every time there’s an update, someone has to go to the hospital and manually install the latest software.
Moving the data and AI to the Internet means Clew will only need to set up the system once per customer. “We won’t need to maintain multiple versions of the same product,” Salomon says.
Clew is not alone among Israeli startups using AI in a healthcare environment. Zebra Medical Vision uses deep-learning algorithms to identify disease from radiological scans, while Belong uses AI to power its cancer-patient social network.
Another Israeli company, Medial EarlySign, uses machine learning to diagnose patients at high risk for specific medical conditions. Its first product, ColonFlag, identifies patients who might develop colorectal cancer.
Clew takes a different approach. Its product is not just an AI-powered research tool but plays an active role in the ICU, allowing doctors to see at a glance the status of every patient in the unit.
Although “the ICU is still our only market and 99 percent of our energy is going into the ICU domain,” Salomon says that Clew hopes to expand to other hospital units where acute patients are cared for, including the operating room.
That expansion was the reason behind a name change at the end of 2017. The company’s previous name, Intensix, was too associated with “intensive care analytics,” Salomon explains. Clew comes from Greek mythology where Ariadne gave a ball of thread (a “clew”) to Theseus so he could use it to find his way out of her father’s labyrinth. Clew Medical hopes to guide doctors and patients through the maze of modern medical data.
Plus, as Salomon points out, “it’s short and easy to pronounce!”
[Photo: Gellerj / Flickr]